Commit
•
77f9210
1
Parent(s):
b4db065
End of training
Browse files- README.md +2 -0
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jan16_21-09-40_d19f5dc858c0/events.out.tfevents.1705443471.d19f5dc858c0.15490.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1350 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.15306122448979592,
|
| 4 |
+
"eval_loss": 3.643535614013672,
|
| 5 |
+
"eval_runtime": 1.6218,
|
| 6 |
+
"eval_samples_per_second": 60.427,
|
| 7 |
+
"eval_steps_per_second": 1.233,
|
| 8 |
+
"train_loss": 3.289549721309117,
|
| 9 |
+
"train_runtime": 4059.8356,
|
| 10 |
+
"train_samples_per_second": 13.597,
|
| 11 |
+
"train_steps_per_second": 0.172
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.15306122448979592,
|
| 4 |
+
"eval_loss": 3.643535614013672,
|
| 5 |
+
"eval_runtime": 1.6218,
|
| 6 |
+
"eval_samples_per_second": 60.427,
|
| 7 |
+
"eval_steps_per_second": 1.233
|
| 8 |
+
}
|
runs/Jan16_21-09-40_d19f5dc858c0/events.out.tfevents.1705443471.d19f5dc858c0.15490.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5cd2bbd5677b8880e42d00bd24b2a403bb291ee85d5cf438a1e29f109fa4a8e
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 3.289549721309117,
|
| 4 |
+
"train_runtime": 4059.8356,
|
| 5 |
+
"train_samples_per_second": 13.597,
|
| 6 |
+
"train_steps_per_second": 0.172
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.643535614013672,
|
| 3 |
+
"best_model_checkpoint": "./drive/MyDrive/repositories/torch_example_image-classification/outputs_letter3/checkpoint-700",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.030612244897959183,
|
| 14 |
+
"eval_loss": 3.945223808288574,
|
| 15 |
+
"eval_runtime": 35.9416,
|
| 16 |
+
"eval_samples_per_second": 2.727,
|
| 17 |
+
"eval_steps_per_second": 0.056,
|
| 18 |
+
"step": 7
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.43,
|
| 22 |
+
"learning_rate": 1.9714285714285718e-05,
|
| 23 |
+
"loss": 3.9498,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.05102040816326531,
|
| 29 |
+
"eval_loss": 3.943814277648926,
|
| 30 |
+
"eval_runtime": 1.6003,
|
| 31 |
+
"eval_samples_per_second": 61.237,
|
| 32 |
+
"eval_steps_per_second": 1.25,
|
| 33 |
+
"step": 14
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.86,
|
| 37 |
+
"learning_rate": 1.942857142857143e-05,
|
| 38 |
+
"loss": 3.9413,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.04081632653061224,
|
| 44 |
+
"eval_loss": 3.9436657428741455,
|
| 45 |
+
"eval_runtime": 1.5584,
|
| 46 |
+
"eval_samples_per_second": 62.886,
|
| 47 |
+
"eval_steps_per_second": 1.283,
|
| 48 |
+
"step": 21
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.04081632653061224,
|
| 53 |
+
"eval_loss": 3.9431352615356445,
|
| 54 |
+
"eval_runtime": 1.6475,
|
| 55 |
+
"eval_samples_per_second": 59.483,
|
| 56 |
+
"eval_steps_per_second": 1.214,
|
| 57 |
+
"step": 28
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.29,
|
| 61 |
+
"learning_rate": 1.9142857142857146e-05,
|
| 62 |
+
"loss": 3.9255,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.04081632653061224,
|
| 68 |
+
"eval_loss": 3.9424338340759277,
|
| 69 |
+
"eval_runtime": 1.5527,
|
| 70 |
+
"eval_samples_per_second": 63.114,
|
| 71 |
+
"eval_steps_per_second": 1.288,
|
| 72 |
+
"step": 35
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.71,
|
| 76 |
+
"learning_rate": 1.885714285714286e-05,
|
| 77 |
+
"loss": 3.9132,
|
| 78 |
+
"step": 40
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.030612244897959183,
|
| 83 |
+
"eval_loss": 3.9400839805603027,
|
| 84 |
+
"eval_runtime": 1.6728,
|
| 85 |
+
"eval_samples_per_second": 58.585,
|
| 86 |
+
"eval_steps_per_second": 1.196,
|
| 87 |
+
"step": 42
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.030612244897959183,
|
| 92 |
+
"eval_loss": 3.937299966812134,
|
| 93 |
+
"eval_runtime": 1.6864,
|
| 94 |
+
"eval_samples_per_second": 58.111,
|
| 95 |
+
"eval_steps_per_second": 1.186,
|
| 96 |
+
"step": 49
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.14,
|
| 100 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 101 |
+
"loss": 3.8913,
|
| 102 |
+
"step": 50
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.02040816326530612,
|
| 107 |
+
"eval_loss": 3.9351377487182617,
|
| 108 |
+
"eval_runtime": 1.7475,
|
| 109 |
+
"eval_samples_per_second": 56.08,
|
| 110 |
+
"eval_steps_per_second": 1.144,
|
| 111 |
+
"step": 56
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.57,
|
| 115 |
+
"learning_rate": 1.8285714285714288e-05,
|
| 116 |
+
"loss": 3.8685,
|
| 117 |
+
"step": 60
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 9.0,
|
| 121 |
+
"eval_accuracy": 0.02040816326530612,
|
| 122 |
+
"eval_loss": 3.931184768676758,
|
| 123 |
+
"eval_runtime": 1.7165,
|
| 124 |
+
"eval_samples_per_second": 57.092,
|
| 125 |
+
"eval_steps_per_second": 1.165,
|
| 126 |
+
"step": 63
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"learning_rate": 1.8e-05,
|
| 131 |
+
"loss": 3.8413,
|
| 132 |
+
"step": 70
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"eval_accuracy": 0.030612244897959183,
|
| 137 |
+
"eval_loss": 3.9259071350097656,
|
| 138 |
+
"eval_runtime": 1.7086,
|
| 139 |
+
"eval_samples_per_second": 57.357,
|
| 140 |
+
"eval_steps_per_second": 1.171,
|
| 141 |
+
"step": 70
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 11.0,
|
| 145 |
+
"eval_accuracy": 0.030612244897959183,
|
| 146 |
+
"eval_loss": 3.9218833446502686,
|
| 147 |
+
"eval_runtime": 1.6006,
|
| 148 |
+
"eval_samples_per_second": 61.228,
|
| 149 |
+
"eval_steps_per_second": 1.25,
|
| 150 |
+
"step": 77
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.43,
|
| 154 |
+
"learning_rate": 1.7714285714285717e-05,
|
| 155 |
+
"loss": 3.8163,
|
| 156 |
+
"step": 80
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 12.0,
|
| 160 |
+
"eval_accuracy": 0.02040816326530612,
|
| 161 |
+
"eval_loss": 3.9182682037353516,
|
| 162 |
+
"eval_runtime": 1.8155,
|
| 163 |
+
"eval_samples_per_second": 53.98,
|
| 164 |
+
"eval_steps_per_second": 1.102,
|
| 165 |
+
"step": 84
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.86,
|
| 169 |
+
"learning_rate": 1.742857142857143e-05,
|
| 170 |
+
"loss": 3.7912,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 13.0,
|
| 175 |
+
"eval_accuracy": 0.04081632653061224,
|
| 176 |
+
"eval_loss": 3.9151253700256348,
|
| 177 |
+
"eval_runtime": 1.704,
|
| 178 |
+
"eval_samples_per_second": 57.511,
|
| 179 |
+
"eval_steps_per_second": 1.174,
|
| 180 |
+
"step": 91
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 14.0,
|
| 184 |
+
"eval_accuracy": 0.030612244897959183,
|
| 185 |
+
"eval_loss": 3.911611795425415,
|
| 186 |
+
"eval_runtime": 1.7037,
|
| 187 |
+
"eval_samples_per_second": 57.521,
|
| 188 |
+
"eval_steps_per_second": 1.174,
|
| 189 |
+
"step": 98
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.29,
|
| 193 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 194 |
+
"loss": 3.7616,
|
| 195 |
+
"step": 100
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 15.0,
|
| 199 |
+
"eval_accuracy": 0.04081632653061224,
|
| 200 |
+
"eval_loss": 3.9074392318725586,
|
| 201 |
+
"eval_runtime": 1.6801,
|
| 202 |
+
"eval_samples_per_second": 58.331,
|
| 203 |
+
"eval_steps_per_second": 1.19,
|
| 204 |
+
"step": 105
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.71,
|
| 208 |
+
"learning_rate": 1.6857142857142858e-05,
|
| 209 |
+
"loss": 3.734,
|
| 210 |
+
"step": 110
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 16.0,
|
| 214 |
+
"eval_accuracy": 0.04081632653061224,
|
| 215 |
+
"eval_loss": 3.9029488563537598,
|
| 216 |
+
"eval_runtime": 1.7659,
|
| 217 |
+
"eval_samples_per_second": 55.496,
|
| 218 |
+
"eval_steps_per_second": 1.133,
|
| 219 |
+
"step": 112
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 17.0,
|
| 223 |
+
"eval_accuracy": 0.061224489795918366,
|
| 224 |
+
"eval_loss": 3.8968818187713623,
|
| 225 |
+
"eval_runtime": 1.6451,
|
| 226 |
+
"eval_samples_per_second": 59.57,
|
| 227 |
+
"eval_steps_per_second": 1.216,
|
| 228 |
+
"step": 119
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 17.14,
|
| 232 |
+
"learning_rate": 1.6571428571428574e-05,
|
| 233 |
+
"loss": 3.7014,
|
| 234 |
+
"step": 120
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 18.0,
|
| 238 |
+
"eval_accuracy": 0.07142857142857142,
|
| 239 |
+
"eval_loss": 3.890695095062256,
|
| 240 |
+
"eval_runtime": 1.6901,
|
| 241 |
+
"eval_samples_per_second": 57.983,
|
| 242 |
+
"eval_steps_per_second": 1.183,
|
| 243 |
+
"step": 126
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.57,
|
| 247 |
+
"learning_rate": 1.6285714285714287e-05,
|
| 248 |
+
"loss": 3.6707,
|
| 249 |
+
"step": 130
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 19.0,
|
| 253 |
+
"eval_accuracy": 0.07142857142857142,
|
| 254 |
+
"eval_loss": 3.8844714164733887,
|
| 255 |
+
"eval_runtime": 1.6505,
|
| 256 |
+
"eval_samples_per_second": 59.374,
|
| 257 |
+
"eval_steps_per_second": 1.212,
|
| 258 |
+
"step": 133
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 263 |
+
"loss": 3.6307,
|
| 264 |
+
"step": 140
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 20.0,
|
| 268 |
+
"eval_accuracy": 0.08163265306122448,
|
| 269 |
+
"eval_loss": 3.877913475036621,
|
| 270 |
+
"eval_runtime": 1.8041,
|
| 271 |
+
"eval_samples_per_second": 54.322,
|
| 272 |
+
"eval_steps_per_second": 1.109,
|
| 273 |
+
"step": 140
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 21.0,
|
| 277 |
+
"eval_accuracy": 0.08163265306122448,
|
| 278 |
+
"eval_loss": 3.8703930377960205,
|
| 279 |
+
"eval_runtime": 1.7575,
|
| 280 |
+
"eval_samples_per_second": 55.762,
|
| 281 |
+
"eval_steps_per_second": 1.138,
|
| 282 |
+
"step": 147
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 21.43,
|
| 286 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 287 |
+
"loss": 3.596,
|
| 288 |
+
"step": 150
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 22.0,
|
| 292 |
+
"eval_accuracy": 0.09183673469387756,
|
| 293 |
+
"eval_loss": 3.8646252155303955,
|
| 294 |
+
"eval_runtime": 1.6598,
|
| 295 |
+
"eval_samples_per_second": 59.042,
|
| 296 |
+
"eval_steps_per_second": 1.205,
|
| 297 |
+
"step": 154
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 22.86,
|
| 301 |
+
"learning_rate": 1.542857142857143e-05,
|
| 302 |
+
"loss": 3.5875,
|
| 303 |
+
"step": 160
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 23.0,
|
| 307 |
+
"eval_accuracy": 0.09183673469387756,
|
| 308 |
+
"eval_loss": 3.8603618144989014,
|
| 309 |
+
"eval_runtime": 1.6878,
|
| 310 |
+
"eval_samples_per_second": 58.065,
|
| 311 |
+
"eval_steps_per_second": 1.185,
|
| 312 |
+
"step": 161
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 24.0,
|
| 316 |
+
"eval_accuracy": 0.09183673469387756,
|
| 317 |
+
"eval_loss": 3.8561482429504395,
|
| 318 |
+
"eval_runtime": 1.6677,
|
| 319 |
+
"eval_samples_per_second": 58.764,
|
| 320 |
+
"eval_steps_per_second": 1.199,
|
| 321 |
+
"step": 168
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 24.29,
|
| 325 |
+
"learning_rate": 1.5142857142857144e-05,
|
| 326 |
+
"loss": 3.5532,
|
| 327 |
+
"step": 170
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 25.0,
|
| 331 |
+
"eval_accuracy": 0.09183673469387756,
|
| 332 |
+
"eval_loss": 3.8509910106658936,
|
| 333 |
+
"eval_runtime": 1.7363,
|
| 334 |
+
"eval_samples_per_second": 56.441,
|
| 335 |
+
"eval_steps_per_second": 1.152,
|
| 336 |
+
"step": 175
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 25.71,
|
| 340 |
+
"learning_rate": 1.4857142857142858e-05,
|
| 341 |
+
"loss": 3.5374,
|
| 342 |
+
"step": 180
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 26.0,
|
| 346 |
+
"eval_accuracy": 0.09183673469387756,
|
| 347 |
+
"eval_loss": 3.844221353530884,
|
| 348 |
+
"eval_runtime": 1.7776,
|
| 349 |
+
"eval_samples_per_second": 55.131,
|
| 350 |
+
"eval_steps_per_second": 1.125,
|
| 351 |
+
"step": 182
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 27.0,
|
| 355 |
+
"eval_accuracy": 0.10204081632653061,
|
| 356 |
+
"eval_loss": 3.83986496925354,
|
| 357 |
+
"eval_runtime": 1.6514,
|
| 358 |
+
"eval_samples_per_second": 59.342,
|
| 359 |
+
"eval_steps_per_second": 1.211,
|
| 360 |
+
"step": 189
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 27.14,
|
| 364 |
+
"learning_rate": 1.4571428571428573e-05,
|
| 365 |
+
"loss": 3.51,
|
| 366 |
+
"step": 190
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 28.0,
|
| 370 |
+
"eval_accuracy": 0.11224489795918367,
|
| 371 |
+
"eval_loss": 3.8350086212158203,
|
| 372 |
+
"eval_runtime": 1.6793,
|
| 373 |
+
"eval_samples_per_second": 58.357,
|
| 374 |
+
"eval_steps_per_second": 1.191,
|
| 375 |
+
"step": 196
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 28.57,
|
| 379 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 380 |
+
"loss": 3.4842,
|
| 381 |
+
"step": 200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 29.0,
|
| 385 |
+
"eval_accuracy": 0.12244897959183673,
|
| 386 |
+
"eval_loss": 3.8296377658843994,
|
| 387 |
+
"eval_runtime": 1.7517,
|
| 388 |
+
"eval_samples_per_second": 55.946,
|
| 389 |
+
"eval_steps_per_second": 1.142,
|
| 390 |
+
"step": 203
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 30.0,
|
| 394 |
+
"learning_rate": 1.4e-05,
|
| 395 |
+
"loss": 3.4495,
|
| 396 |
+
"step": 210
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 30.0,
|
| 400 |
+
"eval_accuracy": 0.12244897959183673,
|
| 401 |
+
"eval_loss": 3.8243255615234375,
|
| 402 |
+
"eval_runtime": 1.7837,
|
| 403 |
+
"eval_samples_per_second": 54.942,
|
| 404 |
+
"eval_steps_per_second": 1.121,
|
| 405 |
+
"step": 210
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 31.0,
|
| 409 |
+
"eval_accuracy": 0.12244897959183673,
|
| 410 |
+
"eval_loss": 3.8213043212890625,
|
| 411 |
+
"eval_runtime": 1.6545,
|
| 412 |
+
"eval_samples_per_second": 59.233,
|
| 413 |
+
"eval_steps_per_second": 1.209,
|
| 414 |
+
"step": 217
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 31.43,
|
| 418 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 419 |
+
"loss": 3.4155,
|
| 420 |
+
"step": 220
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 32.0,
|
| 424 |
+
"eval_accuracy": 0.12244897959183673,
|
| 425 |
+
"eval_loss": 3.815812110900879,
|
| 426 |
+
"eval_runtime": 1.6721,
|
| 427 |
+
"eval_samples_per_second": 58.61,
|
| 428 |
+
"eval_steps_per_second": 1.196,
|
| 429 |
+
"step": 224
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 32.86,
|
| 433 |
+
"learning_rate": 1.3428571428571429e-05,
|
| 434 |
+
"loss": 3.4257,
|
| 435 |
+
"step": 230
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 33.0,
|
| 439 |
+
"eval_accuracy": 0.12244897959183673,
|
| 440 |
+
"eval_loss": 3.8117594718933105,
|
| 441 |
+
"eval_runtime": 1.6581,
|
| 442 |
+
"eval_samples_per_second": 59.102,
|
| 443 |
+
"eval_steps_per_second": 1.206,
|
| 444 |
+
"step": 231
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 34.0,
|
| 448 |
+
"eval_accuracy": 0.1326530612244898,
|
| 449 |
+
"eval_loss": 3.8061439990997314,
|
| 450 |
+
"eval_runtime": 1.6272,
|
| 451 |
+
"eval_samples_per_second": 60.227,
|
| 452 |
+
"eval_steps_per_second": 1.229,
|
| 453 |
+
"step": 238
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 34.29,
|
| 457 |
+
"learning_rate": 1.3142857142857145e-05,
|
| 458 |
+
"loss": 3.395,
|
| 459 |
+
"step": 240
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 35.0,
|
| 463 |
+
"eval_accuracy": 0.1326530612244898,
|
| 464 |
+
"eval_loss": 3.8029837608337402,
|
| 465 |
+
"eval_runtime": 1.6449,
|
| 466 |
+
"eval_samples_per_second": 59.577,
|
| 467 |
+
"eval_steps_per_second": 1.216,
|
| 468 |
+
"step": 245
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 35.71,
|
| 472 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 473 |
+
"loss": 3.3693,
|
| 474 |
+
"step": 250
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 36.0,
|
| 478 |
+
"eval_accuracy": 0.14285714285714285,
|
| 479 |
+
"eval_loss": 3.795672655105591,
|
| 480 |
+
"eval_runtime": 1.6624,
|
| 481 |
+
"eval_samples_per_second": 58.953,
|
| 482 |
+
"eval_steps_per_second": 1.203,
|
| 483 |
+
"step": 252
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 37.0,
|
| 487 |
+
"eval_accuracy": 0.12244897959183673,
|
| 488 |
+
"eval_loss": 3.790419578552246,
|
| 489 |
+
"eval_runtime": 1.6455,
|
| 490 |
+
"eval_samples_per_second": 59.556,
|
| 491 |
+
"eval_steps_per_second": 1.215,
|
| 492 |
+
"step": 259
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 37.14,
|
| 496 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 497 |
+
"loss": 3.35,
|
| 498 |
+
"step": 260
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 38.0,
|
| 502 |
+
"eval_accuracy": 0.12244897959183673,
|
| 503 |
+
"eval_loss": 3.783411741256714,
|
| 504 |
+
"eval_runtime": 1.6562,
|
| 505 |
+
"eval_samples_per_second": 59.172,
|
| 506 |
+
"eval_steps_per_second": 1.208,
|
| 507 |
+
"step": 266
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 38.57,
|
| 511 |
+
"learning_rate": 1.2285714285714288e-05,
|
| 512 |
+
"loss": 3.3453,
|
| 513 |
+
"step": 270
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 39.0,
|
| 517 |
+
"eval_accuracy": 0.12244897959183673,
|
| 518 |
+
"eval_loss": 3.778721332550049,
|
| 519 |
+
"eval_runtime": 1.7932,
|
| 520 |
+
"eval_samples_per_second": 54.651,
|
| 521 |
+
"eval_steps_per_second": 1.115,
|
| 522 |
+
"step": 273
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 40.0,
|
| 526 |
+
"learning_rate": 1.2e-05,
|
| 527 |
+
"loss": 3.2977,
|
| 528 |
+
"step": 280
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 40.0,
|
| 532 |
+
"eval_accuracy": 0.12244897959183673,
|
| 533 |
+
"eval_loss": 3.772735357284546,
|
| 534 |
+
"eval_runtime": 1.6336,
|
| 535 |
+
"eval_samples_per_second": 59.991,
|
| 536 |
+
"eval_steps_per_second": 1.224,
|
| 537 |
+
"step": 280
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 41.0,
|
| 541 |
+
"eval_accuracy": 0.12244897959183673,
|
| 542 |
+
"eval_loss": 3.7680680751800537,
|
| 543 |
+
"eval_runtime": 1.7171,
|
| 544 |
+
"eval_samples_per_second": 57.072,
|
| 545 |
+
"eval_steps_per_second": 1.165,
|
| 546 |
+
"step": 287
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 41.43,
|
| 550 |
+
"learning_rate": 1.1714285714285716e-05,
|
| 551 |
+
"loss": 3.2875,
|
| 552 |
+
"step": 290
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 42.0,
|
| 556 |
+
"eval_accuracy": 0.12244897959183673,
|
| 557 |
+
"eval_loss": 3.762765407562256,
|
| 558 |
+
"eval_runtime": 1.6284,
|
| 559 |
+
"eval_samples_per_second": 60.181,
|
| 560 |
+
"eval_steps_per_second": 1.228,
|
| 561 |
+
"step": 294
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 42.86,
|
| 565 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 566 |
+
"loss": 3.2504,
|
| 567 |
+
"step": 300
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 43.0,
|
| 571 |
+
"eval_accuracy": 0.12244897959183673,
|
| 572 |
+
"eval_loss": 3.758150100708008,
|
| 573 |
+
"eval_runtime": 1.6731,
|
| 574 |
+
"eval_samples_per_second": 58.575,
|
| 575 |
+
"eval_steps_per_second": 1.195,
|
| 576 |
+
"step": 301
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 44.0,
|
| 580 |
+
"eval_accuracy": 0.12244897959183673,
|
| 581 |
+
"eval_loss": 3.7527263164520264,
|
| 582 |
+
"eval_runtime": 1.7657,
|
| 583 |
+
"eval_samples_per_second": 55.502,
|
| 584 |
+
"eval_steps_per_second": 1.133,
|
| 585 |
+
"step": 308
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 44.29,
|
| 589 |
+
"learning_rate": 1.1142857142857143e-05,
|
| 590 |
+
"loss": 3.2772,
|
| 591 |
+
"step": 310
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 45.0,
|
| 595 |
+
"eval_accuracy": 0.12244897959183673,
|
| 596 |
+
"eval_loss": 3.749258041381836,
|
| 597 |
+
"eval_runtime": 1.6842,
|
| 598 |
+
"eval_samples_per_second": 58.188,
|
| 599 |
+
"eval_steps_per_second": 1.188,
|
| 600 |
+
"step": 315
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 45.71,
|
| 604 |
+
"learning_rate": 1.0857142857142858e-05,
|
| 605 |
+
"loss": 3.2353,
|
| 606 |
+
"step": 320
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 46.0,
|
| 610 |
+
"eval_accuracy": 0.11224489795918367,
|
| 611 |
+
"eval_loss": 3.7462167739868164,
|
| 612 |
+
"eval_runtime": 1.6536,
|
| 613 |
+
"eval_samples_per_second": 59.264,
|
| 614 |
+
"eval_steps_per_second": 1.209,
|
| 615 |
+
"step": 322
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 47.0,
|
| 619 |
+
"eval_accuracy": 0.1326530612244898,
|
| 620 |
+
"eval_loss": 3.743089437484741,
|
| 621 |
+
"eval_runtime": 1.639,
|
| 622 |
+
"eval_samples_per_second": 59.793,
|
| 623 |
+
"eval_steps_per_second": 1.22,
|
| 624 |
+
"step": 329
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 47.14,
|
| 628 |
+
"learning_rate": 1.0571428571428572e-05,
|
| 629 |
+
"loss": 3.2198,
|
| 630 |
+
"step": 330
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 48.0,
|
| 634 |
+
"eval_accuracy": 0.1326530612244898,
|
| 635 |
+
"eval_loss": 3.7392406463623047,
|
| 636 |
+
"eval_runtime": 1.6659,
|
| 637 |
+
"eval_samples_per_second": 58.827,
|
| 638 |
+
"eval_steps_per_second": 1.201,
|
| 639 |
+
"step": 336
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 48.57,
|
| 643 |
+
"learning_rate": 1.0285714285714285e-05,
|
| 644 |
+
"loss": 3.204,
|
| 645 |
+
"step": 340
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 49.0,
|
| 649 |
+
"eval_accuracy": 0.14285714285714285,
|
| 650 |
+
"eval_loss": 3.73702073097229,
|
| 651 |
+
"eval_runtime": 1.7576,
|
| 652 |
+
"eval_samples_per_second": 55.758,
|
| 653 |
+
"eval_steps_per_second": 1.138,
|
| 654 |
+
"step": 343
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 50.0,
|
| 658 |
+
"learning_rate": 1e-05,
|
| 659 |
+
"loss": 3.1762,
|
| 660 |
+
"step": 350
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 50.0,
|
| 664 |
+
"eval_accuracy": 0.14285714285714285,
|
| 665 |
+
"eval_loss": 3.733855962753296,
|
| 666 |
+
"eval_runtime": 1.6472,
|
| 667 |
+
"eval_samples_per_second": 59.494,
|
| 668 |
+
"eval_steps_per_second": 1.214,
|
| 669 |
+
"step": 350
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 51.0,
|
| 673 |
+
"eval_accuracy": 0.14285714285714285,
|
| 674 |
+
"eval_loss": 3.730581283569336,
|
| 675 |
+
"eval_runtime": 1.6737,
|
| 676 |
+
"eval_samples_per_second": 58.554,
|
| 677 |
+
"eval_steps_per_second": 1.195,
|
| 678 |
+
"step": 357
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 51.43,
|
| 682 |
+
"learning_rate": 9.714285714285715e-06,
|
| 683 |
+
"loss": 3.1741,
|
| 684 |
+
"step": 360
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 52.0,
|
| 688 |
+
"eval_accuracy": 0.16326530612244897,
|
| 689 |
+
"eval_loss": 3.7267162799835205,
|
| 690 |
+
"eval_runtime": 1.669,
|
| 691 |
+
"eval_samples_per_second": 58.718,
|
| 692 |
+
"eval_steps_per_second": 1.198,
|
| 693 |
+
"step": 364
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 52.86,
|
| 697 |
+
"learning_rate": 9.42857142857143e-06,
|
| 698 |
+
"loss": 3.1757,
|
| 699 |
+
"step": 370
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 53.0,
|
| 703 |
+
"eval_accuracy": 0.16326530612244897,
|
| 704 |
+
"eval_loss": 3.7221927642822266,
|
| 705 |
+
"eval_runtime": 1.6595,
|
| 706 |
+
"eval_samples_per_second": 59.054,
|
| 707 |
+
"eval_steps_per_second": 1.205,
|
| 708 |
+
"step": 371
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 54.0,
|
| 712 |
+
"eval_accuracy": 0.15306122448979592,
|
| 713 |
+
"eval_loss": 3.717994451522827,
|
| 714 |
+
"eval_runtime": 1.6603,
|
| 715 |
+
"eval_samples_per_second": 59.027,
|
| 716 |
+
"eval_steps_per_second": 1.205,
|
| 717 |
+
"step": 378
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 54.29,
|
| 721 |
+
"learning_rate": 9.142857142857144e-06,
|
| 722 |
+
"loss": 3.1492,
|
| 723 |
+
"step": 380
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 55.0,
|
| 727 |
+
"eval_accuracy": 0.15306122448979592,
|
| 728 |
+
"eval_loss": 3.7148733139038086,
|
| 729 |
+
"eval_runtime": 1.6452,
|
| 730 |
+
"eval_samples_per_second": 59.566,
|
| 731 |
+
"eval_steps_per_second": 1.216,
|
| 732 |
+
"step": 385
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 55.71,
|
| 736 |
+
"learning_rate": 8.857142857142858e-06,
|
| 737 |
+
"loss": 3.1442,
|
| 738 |
+
"step": 390
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 56.0,
|
| 742 |
+
"eval_accuracy": 0.15306122448979592,
|
| 743 |
+
"eval_loss": 3.7107248306274414,
|
| 744 |
+
"eval_runtime": 1.6947,
|
| 745 |
+
"eval_samples_per_second": 57.827,
|
| 746 |
+
"eval_steps_per_second": 1.18,
|
| 747 |
+
"step": 392
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 57.0,
|
| 751 |
+
"eval_accuracy": 0.15306122448979592,
|
| 752 |
+
"eval_loss": 3.7084951400756836,
|
| 753 |
+
"eval_runtime": 1.6087,
|
| 754 |
+
"eval_samples_per_second": 60.919,
|
| 755 |
+
"eval_steps_per_second": 1.243,
|
| 756 |
+
"step": 399
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 57.14,
|
| 760 |
+
"learning_rate": 8.571428571428571e-06,
|
| 761 |
+
"loss": 3.1174,
|
| 762 |
+
"step": 400
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 58.0,
|
| 766 |
+
"eval_accuracy": 0.15306122448979592,
|
| 767 |
+
"eval_loss": 3.705909013748169,
|
| 768 |
+
"eval_runtime": 1.7081,
|
| 769 |
+
"eval_samples_per_second": 57.372,
|
| 770 |
+
"eval_steps_per_second": 1.171,
|
| 771 |
+
"step": 406
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 58.57,
|
| 775 |
+
"learning_rate": 8.285714285714287e-06,
|
| 776 |
+
"loss": 3.0962,
|
| 777 |
+
"step": 410
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 59.0,
|
| 781 |
+
"eval_accuracy": 0.15306122448979592,
|
| 782 |
+
"eval_loss": 3.7031126022338867,
|
| 783 |
+
"eval_runtime": 1.5815,
|
| 784 |
+
"eval_samples_per_second": 61.967,
|
| 785 |
+
"eval_steps_per_second": 1.265,
|
| 786 |
+
"step": 413
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 60.0,
|
| 790 |
+
"learning_rate": 8.000000000000001e-06,
|
| 791 |
+
"loss": 3.1237,
|
| 792 |
+
"step": 420
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 60.0,
|
| 796 |
+
"eval_accuracy": 0.15306122448979592,
|
| 797 |
+
"eval_loss": 3.701946258544922,
|
| 798 |
+
"eval_runtime": 1.7026,
|
| 799 |
+
"eval_samples_per_second": 57.559,
|
| 800 |
+
"eval_steps_per_second": 1.175,
|
| 801 |
+
"step": 420
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 61.0,
|
| 805 |
+
"eval_accuracy": 0.15306122448979592,
|
| 806 |
+
"eval_loss": 3.6996471881866455,
|
| 807 |
+
"eval_runtime": 1.6975,
|
| 808 |
+
"eval_samples_per_second": 57.732,
|
| 809 |
+
"eval_steps_per_second": 1.178,
|
| 810 |
+
"step": 427
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 61.43,
|
| 814 |
+
"learning_rate": 7.714285714285716e-06,
|
| 815 |
+
"loss": 3.1229,
|
| 816 |
+
"step": 430
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 62.0,
|
| 820 |
+
"eval_accuracy": 0.15306122448979592,
|
| 821 |
+
"eval_loss": 3.6955974102020264,
|
| 822 |
+
"eval_runtime": 1.6826,
|
| 823 |
+
"eval_samples_per_second": 58.242,
|
| 824 |
+
"eval_steps_per_second": 1.189,
|
| 825 |
+
"step": 434
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 62.86,
|
| 829 |
+
"learning_rate": 7.428571428571429e-06,
|
| 830 |
+
"loss": 3.0946,
|
| 831 |
+
"step": 440
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 63.0,
|
| 835 |
+
"eval_accuracy": 0.15306122448979592,
|
| 836 |
+
"eval_loss": 3.692981719970703,
|
| 837 |
+
"eval_runtime": 1.7683,
|
| 838 |
+
"eval_samples_per_second": 55.42,
|
| 839 |
+
"eval_steps_per_second": 1.131,
|
| 840 |
+
"step": 441
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 64.0,
|
| 844 |
+
"eval_accuracy": 0.15306122448979592,
|
| 845 |
+
"eval_loss": 3.6915957927703857,
|
| 846 |
+
"eval_runtime": 1.6752,
|
| 847 |
+
"eval_samples_per_second": 58.501,
|
| 848 |
+
"eval_steps_per_second": 1.194,
|
| 849 |
+
"step": 448
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 64.29,
|
| 853 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 854 |
+
"loss": 3.0861,
|
| 855 |
+
"step": 450
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 65.0,
|
| 859 |
+
"eval_accuracy": 0.15306122448979592,
|
| 860 |
+
"eval_loss": 3.6893138885498047,
|
| 861 |
+
"eval_runtime": 1.6711,
|
| 862 |
+
"eval_samples_per_second": 58.644,
|
| 863 |
+
"eval_steps_per_second": 1.197,
|
| 864 |
+
"step": 455
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 65.71,
|
| 868 |
+
"learning_rate": 6.857142857142858e-06,
|
| 869 |
+
"loss": 3.0406,
|
| 870 |
+
"step": 460
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 66.0,
|
| 874 |
+
"eval_accuracy": 0.15306122448979592,
|
| 875 |
+
"eval_loss": 3.6859352588653564,
|
| 876 |
+
"eval_runtime": 1.7238,
|
| 877 |
+
"eval_samples_per_second": 56.85,
|
| 878 |
+
"eval_steps_per_second": 1.16,
|
| 879 |
+
"step": 462
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 67.0,
|
| 883 |
+
"eval_accuracy": 0.15306122448979592,
|
| 884 |
+
"eval_loss": 3.6839077472686768,
|
| 885 |
+
"eval_runtime": 1.6549,
|
| 886 |
+
"eval_samples_per_second": 59.218,
|
| 887 |
+
"eval_steps_per_second": 1.209,
|
| 888 |
+
"step": 469
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 67.14,
|
| 892 |
+
"learning_rate": 6.571428571428572e-06,
|
| 893 |
+
"loss": 3.077,
|
| 894 |
+
"step": 470
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 68.0,
|
| 898 |
+
"eval_accuracy": 0.15306122448979592,
|
| 899 |
+
"eval_loss": 3.6815552711486816,
|
| 900 |
+
"eval_runtime": 1.673,
|
| 901 |
+
"eval_samples_per_second": 58.578,
|
| 902 |
+
"eval_steps_per_second": 1.195,
|
| 903 |
+
"step": 476
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 68.57,
|
| 907 |
+
"learning_rate": 6.285714285714286e-06,
|
| 908 |
+
"loss": 3.0555,
|
| 909 |
+
"step": 480
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 69.0,
|
| 913 |
+
"eval_accuracy": 0.15306122448979592,
|
| 914 |
+
"eval_loss": 3.678163766860962,
|
| 915 |
+
"eval_runtime": 1.6518,
|
| 916 |
+
"eval_samples_per_second": 59.329,
|
| 917 |
+
"eval_steps_per_second": 1.211,
|
| 918 |
+
"step": 483
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 70.0,
|
| 922 |
+
"learning_rate": 6e-06,
|
| 923 |
+
"loss": 3.035,
|
| 924 |
+
"step": 490
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 70.0,
|
| 928 |
+
"eval_accuracy": 0.15306122448979592,
|
| 929 |
+
"eval_loss": 3.6762583255767822,
|
| 930 |
+
"eval_runtime": 1.6591,
|
| 931 |
+
"eval_samples_per_second": 59.069,
|
| 932 |
+
"eval_steps_per_second": 1.205,
|
| 933 |
+
"step": 490
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 71.0,
|
| 937 |
+
"eval_accuracy": 0.15306122448979592,
|
| 938 |
+
"eval_loss": 3.672853469848633,
|
| 939 |
+
"eval_runtime": 1.6495,
|
| 940 |
+
"eval_samples_per_second": 59.412,
|
| 941 |
+
"eval_steps_per_second": 1.212,
|
| 942 |
+
"step": 497
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 71.43,
|
| 946 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 947 |
+
"loss": 3.0246,
|
| 948 |
+
"step": 500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 72.0,
|
| 952 |
+
"eval_accuracy": 0.15306122448979592,
|
| 953 |
+
"eval_loss": 3.6719117164611816,
|
| 954 |
+
"eval_runtime": 1.6901,
|
| 955 |
+
"eval_samples_per_second": 57.986,
|
| 956 |
+
"eval_steps_per_second": 1.183,
|
| 957 |
+
"step": 504
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 72.86,
|
| 961 |
+
"learning_rate": 5.428571428571429e-06,
|
| 962 |
+
"loss": 3.0282,
|
| 963 |
+
"step": 510
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 73.0,
|
| 967 |
+
"eval_accuracy": 0.15306122448979592,
|
| 968 |
+
"eval_loss": 3.670848846435547,
|
| 969 |
+
"eval_runtime": 1.7293,
|
| 970 |
+
"eval_samples_per_second": 56.669,
|
| 971 |
+
"eval_steps_per_second": 1.157,
|
| 972 |
+
"step": 511
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 74.0,
|
| 976 |
+
"eval_accuracy": 0.14285714285714285,
|
| 977 |
+
"eval_loss": 3.6683461666107178,
|
| 978 |
+
"eval_runtime": 1.6959,
|
| 979 |
+
"eval_samples_per_second": 57.785,
|
| 980 |
+
"eval_steps_per_second": 1.179,
|
| 981 |
+
"step": 518
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 74.29,
|
| 985 |
+
"learning_rate": 5.142857142857142e-06,
|
| 986 |
+
"loss": 3.0293,
|
| 987 |
+
"step": 520
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 75.0,
|
| 991 |
+
"eval_accuracy": 0.14285714285714285,
|
| 992 |
+
"eval_loss": 3.665170669555664,
|
| 993 |
+
"eval_runtime": 1.6438,
|
| 994 |
+
"eval_samples_per_second": 59.617,
|
| 995 |
+
"eval_steps_per_second": 1.217,
|
| 996 |
+
"step": 525
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 75.71,
|
| 1000 |
+
"learning_rate": 4.857142857142858e-06,
|
| 1001 |
+
"loss": 2.9893,
|
| 1002 |
+
"step": 530
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 76.0,
|
| 1006 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1007 |
+
"eval_loss": 3.66402268409729,
|
| 1008 |
+
"eval_runtime": 1.6852,
|
| 1009 |
+
"eval_samples_per_second": 58.155,
|
| 1010 |
+
"eval_steps_per_second": 1.187,
|
| 1011 |
+
"step": 532
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 77.0,
|
| 1015 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1016 |
+
"eval_loss": 3.6634998321533203,
|
| 1017 |
+
"eval_runtime": 1.7537,
|
| 1018 |
+
"eval_samples_per_second": 55.882,
|
| 1019 |
+
"eval_steps_per_second": 1.14,
|
| 1020 |
+
"step": 539
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 77.14,
|
| 1024 |
+
"learning_rate": 4.571428571428572e-06,
|
| 1025 |
+
"loss": 2.9888,
|
| 1026 |
+
"step": 540
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 78.0,
|
| 1030 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1031 |
+
"eval_loss": 3.6618170738220215,
|
| 1032 |
+
"eval_runtime": 1.7774,
|
| 1033 |
+
"eval_samples_per_second": 55.135,
|
| 1034 |
+
"eval_steps_per_second": 1.125,
|
| 1035 |
+
"step": 546
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 78.57,
|
| 1039 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 1040 |
+
"loss": 2.9833,
|
| 1041 |
+
"step": 550
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 79.0,
|
| 1045 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1046 |
+
"eval_loss": 3.659451484680176,
|
| 1047 |
+
"eval_runtime": 1.6474,
|
| 1048 |
+
"eval_samples_per_second": 59.487,
|
| 1049 |
+
"eval_steps_per_second": 1.214,
|
| 1050 |
+
"step": 553
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 80.0,
|
| 1054 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1055 |
+
"loss": 2.9739,
|
| 1056 |
+
"step": 560
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 80.0,
|
| 1060 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1061 |
+
"eval_loss": 3.6578376293182373,
|
| 1062 |
+
"eval_runtime": 1.6531,
|
| 1063 |
+
"eval_samples_per_second": 59.283,
|
| 1064 |
+
"eval_steps_per_second": 1.21,
|
| 1065 |
+
"step": 560
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 81.0,
|
| 1069 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1070 |
+
"eval_loss": 3.656160593032837,
|
| 1071 |
+
"eval_runtime": 1.7409,
|
| 1072 |
+
"eval_samples_per_second": 56.294,
|
| 1073 |
+
"eval_steps_per_second": 1.149,
|
| 1074 |
+
"step": 567
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 81.43,
|
| 1078 |
+
"learning_rate": 3.7142857142857146e-06,
|
| 1079 |
+
"loss": 2.9513,
|
| 1080 |
+
"step": 570
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 82.0,
|
| 1084 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1085 |
+
"eval_loss": 3.655242681503296,
|
| 1086 |
+
"eval_runtime": 1.6811,
|
| 1087 |
+
"eval_samples_per_second": 58.294,
|
| 1088 |
+
"eval_steps_per_second": 1.19,
|
| 1089 |
+
"step": 574
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 82.86,
|
| 1093 |
+
"learning_rate": 3.428571428571429e-06,
|
| 1094 |
+
"loss": 2.9503,
|
| 1095 |
+
"step": 580
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 83.0,
|
| 1099 |
+
"eval_accuracy": 0.14285714285714285,
|
| 1100 |
+
"eval_loss": 3.6539218425750732,
|
| 1101 |
+
"eval_runtime": 1.7574,
|
| 1102 |
+
"eval_samples_per_second": 55.764,
|
| 1103 |
+
"eval_steps_per_second": 1.138,
|
| 1104 |
+
"step": 581
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 84.0,
|
| 1108 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1109 |
+
"eval_loss": 3.653193950653076,
|
| 1110 |
+
"eval_runtime": 1.6302,
|
| 1111 |
+
"eval_samples_per_second": 60.114,
|
| 1112 |
+
"eval_steps_per_second": 1.227,
|
| 1113 |
+
"step": 588
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 84.29,
|
| 1117 |
+
"learning_rate": 3.142857142857143e-06,
|
| 1118 |
+
"loss": 2.9792,
|
| 1119 |
+
"step": 590
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 85.0,
|
| 1123 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1124 |
+
"eval_loss": 3.651691436767578,
|
| 1125 |
+
"eval_runtime": 1.7277,
|
| 1126 |
+
"eval_samples_per_second": 56.724,
|
| 1127 |
+
"eval_steps_per_second": 1.158,
|
| 1128 |
+
"step": 595
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 85.71,
|
| 1132 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 1133 |
+
"loss": 2.9561,
|
| 1134 |
+
"step": 600
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 86.0,
|
| 1138 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1139 |
+
"eval_loss": 3.6496691703796387,
|
| 1140 |
+
"eval_runtime": 1.6772,
|
| 1141 |
+
"eval_samples_per_second": 58.432,
|
| 1142 |
+
"eval_steps_per_second": 1.192,
|
| 1143 |
+
"step": 602
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 87.0,
|
| 1147 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1148 |
+
"eval_loss": 3.6485908031463623,
|
| 1149 |
+
"eval_runtime": 1.664,
|
| 1150 |
+
"eval_samples_per_second": 58.893,
|
| 1151 |
+
"eval_steps_per_second": 1.202,
|
| 1152 |
+
"step": 609
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 87.14,
|
| 1156 |
+
"learning_rate": 2.571428571428571e-06,
|
| 1157 |
+
"loss": 2.964,
|
| 1158 |
+
"step": 610
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 88.0,
|
| 1162 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1163 |
+
"eval_loss": 3.647573709487915,
|
| 1164 |
+
"eval_runtime": 1.7778,
|
| 1165 |
+
"eval_samples_per_second": 55.124,
|
| 1166 |
+
"eval_steps_per_second": 1.125,
|
| 1167 |
+
"step": 616
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 88.57,
|
| 1171 |
+
"learning_rate": 2.285714285714286e-06,
|
| 1172 |
+
"loss": 2.9665,
|
| 1173 |
+
"step": 620
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 89.0,
|
| 1177 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1178 |
+
"eval_loss": 3.6470184326171875,
|
| 1179 |
+
"eval_runtime": 1.6689,
|
| 1180 |
+
"eval_samples_per_second": 58.722,
|
| 1181 |
+
"eval_steps_per_second": 1.198,
|
| 1182 |
+
"step": 623
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 90.0,
|
| 1186 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1187 |
+
"loss": 2.9439,
|
| 1188 |
+
"step": 630
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 90.0,
|
| 1192 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1193 |
+
"eval_loss": 3.646164894104004,
|
| 1194 |
+
"eval_runtime": 2.2025,
|
| 1195 |
+
"eval_samples_per_second": 44.495,
|
| 1196 |
+
"eval_steps_per_second": 0.908,
|
| 1197 |
+
"step": 630
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 91.0,
|
| 1201 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1202 |
+
"eval_loss": 3.6452953815460205,
|
| 1203 |
+
"eval_runtime": 1.6826,
|
| 1204 |
+
"eval_samples_per_second": 58.242,
|
| 1205 |
+
"eval_steps_per_second": 1.189,
|
| 1206 |
+
"step": 637
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 91.43,
|
| 1210 |
+
"learning_rate": 1.7142857142857145e-06,
|
| 1211 |
+
"loss": 2.9369,
|
| 1212 |
+
"step": 640
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 92.0,
|
| 1216 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1217 |
+
"eval_loss": 3.645128011703491,
|
| 1218 |
+
"eval_runtime": 1.646,
|
| 1219 |
+
"eval_samples_per_second": 59.539,
|
| 1220 |
+
"eval_steps_per_second": 1.215,
|
| 1221 |
+
"step": 644
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 92.86,
|
| 1225 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 1226 |
+
"loss": 2.9619,
|
| 1227 |
+
"step": 650
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 93.0,
|
| 1231 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1232 |
+
"eval_loss": 3.64505934715271,
|
| 1233 |
+
"eval_runtime": 1.7663,
|
| 1234 |
+
"eval_samples_per_second": 55.483,
|
| 1235 |
+
"eval_steps_per_second": 1.132,
|
| 1236 |
+
"step": 651
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 94.0,
|
| 1240 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1241 |
+
"eval_loss": 3.6448814868927,
|
| 1242 |
+
"eval_runtime": 1.6466,
|
| 1243 |
+
"eval_samples_per_second": 59.516,
|
| 1244 |
+
"eval_steps_per_second": 1.215,
|
| 1245 |
+
"step": 658
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 94.29,
|
| 1249 |
+
"learning_rate": 1.142857142857143e-06,
|
| 1250 |
+
"loss": 2.955,
|
| 1251 |
+
"step": 660
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 95.0,
|
| 1255 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1256 |
+
"eval_loss": 3.6444060802459717,
|
| 1257 |
+
"eval_runtime": 1.6863,
|
| 1258 |
+
"eval_samples_per_second": 58.115,
|
| 1259 |
+
"eval_steps_per_second": 1.186,
|
| 1260 |
+
"step": 665
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 95.71,
|
| 1264 |
+
"learning_rate": 8.571428571428572e-07,
|
| 1265 |
+
"loss": 2.9323,
|
| 1266 |
+
"step": 670
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 96.0,
|
| 1270 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1271 |
+
"eval_loss": 3.6440815925598145,
|
| 1272 |
+
"eval_runtime": 1.626,
|
| 1273 |
+
"eval_samples_per_second": 60.271,
|
| 1274 |
+
"eval_steps_per_second": 1.23,
|
| 1275 |
+
"step": 672
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 97.0,
|
| 1279 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1280 |
+
"eval_loss": 3.6438138484954834,
|
| 1281 |
+
"eval_runtime": 1.7724,
|
| 1282 |
+
"eval_samples_per_second": 55.292,
|
| 1283 |
+
"eval_steps_per_second": 1.128,
|
| 1284 |
+
"step": 679
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 97.14,
|
| 1288 |
+
"learning_rate": 5.714285714285715e-07,
|
| 1289 |
+
"loss": 2.9466,
|
| 1290 |
+
"step": 680
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 98.0,
|
| 1294 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1295 |
+
"eval_loss": 3.643672466278076,
|
| 1296 |
+
"eval_runtime": 1.7638,
|
| 1297 |
+
"eval_samples_per_second": 55.56,
|
| 1298 |
+
"eval_steps_per_second": 1.134,
|
| 1299 |
+
"step": 686
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 98.57,
|
| 1303 |
+
"learning_rate": 2.8571428571428575e-07,
|
| 1304 |
+
"loss": 2.945,
|
| 1305 |
+
"step": 690
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 99.0,
|
| 1309 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1310 |
+
"eval_loss": 3.6435706615448,
|
| 1311 |
+
"eval_runtime": 1.6937,
|
| 1312 |
+
"eval_samples_per_second": 57.862,
|
| 1313 |
+
"eval_steps_per_second": 1.181,
|
| 1314 |
+
"step": 693
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 100.0,
|
| 1318 |
+
"learning_rate": 0.0,
|
| 1319 |
+
"loss": 2.9665,
|
| 1320 |
+
"step": 700
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 100.0,
|
| 1324 |
+
"eval_accuracy": 0.15306122448979592,
|
| 1325 |
+
"eval_loss": 3.643535614013672,
|
| 1326 |
+
"eval_runtime": 1.66,
|
| 1327 |
+
"eval_samples_per_second": 59.037,
|
| 1328 |
+
"eval_steps_per_second": 1.205,
|
| 1329 |
+
"step": 700
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 100.0,
|
| 1333 |
+
"step": 700,
|
| 1334 |
+
"total_flos": 4.2794747466153984e+18,
|
| 1335 |
+
"train_loss": 3.289549721309117,
|
| 1336 |
+
"train_runtime": 4059.8356,
|
| 1337 |
+
"train_samples_per_second": 13.597,
|
| 1338 |
+
"train_steps_per_second": 0.172
|
| 1339 |
+
}
|
| 1340 |
+
],
|
| 1341 |
+
"logging_steps": 10,
|
| 1342 |
+
"max_steps": 700,
|
| 1343 |
+
"num_input_tokens_seen": 0,
|
| 1344 |
+
"num_train_epochs": 100,
|
| 1345 |
+
"save_steps": 500,
|
| 1346 |
+
"total_flos": 4.2794747466153984e+18,
|
| 1347 |
+
"train_batch_size": 80,
|
| 1348 |
+
"trial_name": null,
|
| 1349 |
+
"trial_params": null
|
| 1350 |
+
}
|